| { | |
| "architectures": [ | |
| "BertModel" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "directionality": "bidi", | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 514, | |
| "model_type": "bert", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "pad_token_id": 1, | |
| "pooler_fc_size": 768, | |
| "pooler_num_attention_heads": 12, | |
| "pooler_num_fc_layers": 3, | |
| "pooler_size_per_head": 128, | |
| "pooler_type": "first_token_transform", | |
| "tokenizer_class": "HerbertTokenizerFast", | |
| "type_vocab_size": 2, | |
| "vocab_size": 50000 | |
| } | |